I’m struggling to find a good balance between the usage of AI and working in the Engine. I’m trying to use to implement some of the parts of the game, and I’m trying to focus on the:
- Request a plan of action for feature
- Review the plan of action
- Ask for the execution of the plan
But the plan is already broken, dozens of issues in the planning already. I can see some good ideas, some good principles, but a deeper look and I can see the flaws in the plan. Should I invest more time the planning? Or invest more time refining on the implementation of the plan?
From those who use this type of tooling, what is the workflow that gives the 100x productivity boost that is claimed.
I’m not an expert in Game Dev, but I can see “good” code and “bad” code.
And yet, I can’t see the meaningful benefit, I can see the cracks, it’s never “fully” there, it’s always a couple details that aren’t correct in the planing, it’s always something that bothers, or some misleading thing that looks “ok”, but when you think little bit more it’s not trully correct.
Oh. I didn’t say it is useful for full human code writing replacement. Just that ANY speed boost would only be achievable by someone who already has the skills required to do the job quickly and accurately.